The ABL90 FLEX analyzer is a portable, automated analyzer that measures pH, blood gases, electrolytes, glucose, lactate, and oximetry in heparinised whole blood. The ABL90 FLEX analyzer is intended for use by trained technologists, nurses, physicians and therapists. It is intended for use in a laboratory environment, near patient or point-of-care setting. These tests are only performed under a physician's order.
Device Story
The ABL90 FLEX is a portable, automated analyzer for in vitro testing of heparinized whole blood. It measures pH, blood gases, electrolytes, glucose, lactate, and oximetry parameters (total hemoglobin, oxygen saturation, and hemoglobin fractions). The device is used in laboratory, near-patient, or point-of-care settings by trained clinicians. It utilizes potentiometry for blood gases and electrolytes, and amperometry for metabolites (glucose, lactate). The modification introduces software-based suppression of glucose results under specific low pO2 conditions to prevent falsely low readings caused by glucose oxidase interference. The device displays results on a touch screen; clinicians use these outputs to diagnose and manage metabolic and acid-base disorders. The system ensures clinical accuracy by suppressing unreliable glucose data when pO2 is <10 mmHg or when pO2 is 10-25 mmHg with glucose >270 mg/dL.
Clinical Evidence
Bench testing only. Precision study (20-day, CLSI EP5-A2) evaluated glucose performance across three pO2 levels (10, 30, >90 mmHg) with 240 runs per combination. Interference study (n=1512) confirmed bias < 10% for glucose < 270 mg/dL at pO2 10-25 mmHg. Method comparison study against ABL735 (n=510 per analyzer pair) demonstrated R2 ≥ 0.984, confirming equivalence in the specified pO2 range.
Technological Characteristics
Portable, automated analyzer. Sensing: potentiometry (pH, pO2, pCO2, electrolytes) and amperometry (glucose, lactate). Spectrophotometry for hemoglobin. Connectivity: menu-driven touch screen. Power: 230/120 V mains. Software: Microsoft XPE operating system. Modification: software-based result suppression logic.
Indications for Use
Indicated for patients requiring measurement of pH, blood gases, electrolytes, glucose, lactate, and oximetry in heparinized whole blood for diagnosis and treatment of acid-base disturbances, electrolyte imbalances, carbohydrate metabolism disorders (e.g., diabetes, hypoglycemia), lactic acidosis, anemia, and carbon monoxide poisoning.
Regulatory Classification
Identification
A blood gases (PCO2 , PO2 ) and blood pH test system is a device intended to measure certain gases in blood, serum, plasma or pH of blood, serum, and plasma. Measurements of blood gases (PCO2 , PO2 ) and blood pH are used in the diagnosis and treatment of life-threatening acid-base disturbances.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY AND INSTRUMENT COMBINATION TEMPLATE
A. 510(k) Number:
k131988
B. Purpose for Submission:
Device modification- software and labeling changes to the glucose assay only.
C. Measurand:
pH, pO2, pCO2, potassium, sodium, calcium, chloride, glucose, lactate, total hemoglobin, oxygen saturation, FO2Hb, FCOHb, FHHb and FHbF.
D. Type of Test:
Quantitative - Sensors using Potentiometry, Amperometry, Spectrophotometry, and an Optical System for pO2 measurement.
E. Applicant:
Radiometer Medical ApS
F. Proprietary and Established Names:
ABL90 FLEX
G. Regulatory Information:
1. Regulation section:
21CFR 862.1120: Blood gases (pCO2 and pO2) and blood pH test system.
21CFR 862.1600: Potassium test system.
21CFR 862.1345: Glucose test system.
21CFR 862.1170: Chloride test system.
21CFR 864.7425: Carboxyhemoglobin assay.
21CFR 864.5620: Automated hemoglobin system.
21CFR 862.1145: Calcium test system.
21CFR 862.1665: Sodium test system.
21CFR 862.1150: Calibrator.
21CFR 864.7455: Fetal hemoglobin assay.
21CFR 862.1660: Quality control material (assayed and unassayed).
21CFR 862.1450: Lactic acid test system.
{1}
2. Classification:
Class II, II, II, II, II, II, II, II, II, I (reserved), I (limitation to exemption per 21 CFR 862.9 (c)(9)), respectively
3. Product code:
CHL - BLOOD GASES AND BLOOD PH
CEM - ELECTRODE, ION SPECIFIC, POTASSIUM
CGA - GLUCOSE OXIDASE, GLUCOSE
CGZ - ELECTRODE, ION-SPECIFIC, CHLORIDE
GHS - ASSAY, CARBOXYHEMOGLOBIN
GKR - SYSTEM, HEMOGLOBIN, AUTOMATED
JFP - ELECTRODE, ION SPECIFIC, CALCIUM
JGS - ELECTRODE, ION SPECIFIC, SODIUM
JIX - CALIBRATOR, MULTI-ANALYTE MIXTURE
KQI - ASSAY, FETAL HEMOGLOBIN
JJY - MULTI-ANALYTE CONTROLS, ALL KINDS (ASSAYED AND UNASSAYED)
KHP - ACID, LACTIC, ENZYMATIC METHOD
4. Panel:
Clinical Chemistry (75) and Hematology (81)
H. Intended Use:
1. Intended use(s):
See indications for use below
2. Indication(s) for use:
The ABL90 FLEX analyzer is a portable, automated analyzer that measures pH, blood gases, electrolytes, glucose, lactate, and oximetry in heparinised whole blood. The ABL90 FLEX analyzer is intended for use by trained technologists, nurses, physicians and therapists. It is intended for use in a laboratory environment, near patient or point-of-care setting. These tests are only performed under a physician's order.
Indications for use:
pH, pO2 and pCO2: pH, pCO2 and pO2 measurements are used in the diagnosis and treatment of life-threatening acid-base disturbances.
Potassium (cK+): potassium measurements are used to monitor electrolyte balance in the diagnosis and treatment of disease conditions characterized by low or high blood potassium levels.
Sodium (cNa+): sodium measurements are used in the diagnosis and treatment of aldosteronism, diabetes insipidus, adrenal hypertension, Addison's disease, dehydration, inappropriate antidiuretic secretion, or other diseases involving electrolyte imbalance.
Calcium (cCa2+): calcium measurements are used in the diagnosis and treatment of parathyroid disease, a variety of bone diseases, chronic renal disease and tetany.
Chloride (cCl–): chloride measurements are used in the diagnosis and treatment of electrolyte and metabolic disorders such as cystic fibrosis and diabetic acidosis.
{2}
Glucose (cGlu): glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus and idiopathic hypoglycemia, and of pancreatic islet cell carcinoma.
Lactate (cLac): The lactate measurements measure the concentration of lactate in plasma. Lactate measurements are used to evaluate the acid-base status and are used in the diagnosis and treatment of lactic acidosis (abnormally high acidity of the blood.)
Total Hemoglobin (ctHb): total hemoglobin measurements are used to measure the hemoglobin content of whole blood for the detection of anemia.
sO2: oxygen saturation, more specifically the ratio between the concentration of oxyhemoglobin and oxyhemoglobin plus reduced hemoglobin.
FO2Hb: oxyhemoglobin as a fraction of total hemoglobin.
FCOHb: carboxyhemoglobin measurements are used to determine the carboxyhemoglobin content of human blood as an aid in the diagnosis of carbon monoxide poisoning.
FMetHb: methemoglobin as a fraction of total hemoglobin.
FHHb: reduced hemoglobin as a fraction of total hemoglobin.
Fraction of Fetal Hemoglobin (FHbF): FHbF indicates the amount of fetal hemoglobin. FHbF is seldom used clinically.
3. Special conditions for use statement(s):
For prescription use only.
4. Special instrument requirements:
ABL90 FLEX analyzer
I. Device Description:
The ABL90 FLEX is a portable, automated system intended for in vitro testing of samples of whole blood for the parameters pH, pO2, pCO2, potassium, sodium, calcium, chloride, glucose, lactate, and co-oximetry parameters (total hemoglobin, oxygen saturation, and the hemoglobin fractions FO2Hb, FCOHb, F MetHb, FHHb and FHbF).
J. Substantial Equivalence Information:
1. Predicate device name(s): ABL90 FLEX
2. Predicate 510(k) number(s): k122729
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device ABL90 Flex | Predicate ABL90 Flex (k122729) |
| | The ABL90 FLEX analyzer is a portable, automated | |
{3}
| Similarities | | |
| --- | --- | --- |
| Item | Device ABL90 Flex | Predicate ABL90 Flex (k122729) |
| Intended use | analyzer that measures pH, blood gases, electrolytes, glucose, lactate, and oximetry in heparinized whole blood. The ABL90 FLEX analyzer is intended for use by trained technologists, nurses, physicians and therapists. It is intended for use in a laboratory environment, near patient or point-of-care setting. These tests are only performed under a physician's order. | Same |
| Intended use site | Laboratory and point-of-care. | Same |
| Blood Gas Measurement | pH, pO2, pCO2 by potentiometry | Same |
| Electrolyte Measurement | cK+, cNa+, cCa2+, cCl- by potentiometry | Same |
| Metabolite Measurement | cGlu, cLac by amperometry Glucose: Oxidase | Same |
| Oximetry Measurement | ctHb, sO2 FO2Hb, FHHb, FCOHb, FMetHb, FHbF | Same |
| User Interface | Menu driven touch screen | Same |
| Software operating system | Microsoft XPE | Same |
| Sample Introduction | Aspiration | Same |
| Dimensions (height x width x depth) | 17.7 x 9.8 x 11.4 | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device ABL90 Flex | Predicate ABL90 Flex (k122729) |
| Caution in Manual | Low pO2 levels can influence the linearity of glucose measurements, and can therefore result in falsely low glucose results. Please note that glucose performance is not specified | Low pO2 levels can influence the linearity of glucose measurements, and can therefore result in falsely low glucose results. Please note that glucose performance is not |
{4}
| Differences | | |
| --- | --- | --- |
| Item | Device
ABL90 Flex | Predicate
ABL90 Flex (k122729) |
| | when the pO2 is less than 10 mmHg (1.33 kPa).
The linearity of the glucose is dependent on the oxygen tension of the sample. This dependence is due to the co-reaction of glucose and oxygen by the enzyme glucose oxidase. Low pO2 levels can influence the linearity of the glucose sensor. A table which outlines the glucose linearity as a function of the pO2 is provided in the operators’ manual. | specified when the pO2 is less than 25 mmHg (3.33 kPa).
The linearity of the glucose is dependent on the oxygen tension of the sample. This dependence is due to the co-reaction of glucose and oxygen by the enzyme glucose oxidase. Low pO2 levels can influence the linearity of the glucose sensor. A table which outlines the glucose linearity as a function of the pO2 is provided in the operators’ manual. |
| Software change | Software changes:
- Suppression of glucose results when pO2 < 10 mmHg
- Suppression of glucose results >270mg/dL when pO2 is between 10 - 25mmHg
- Message: “Glu not usable” | Software changes:
- Suppression of glucose results when pO2 < 25 mmHg
- Message: “Glu not usable” |
## K. Standard/Guidance Document Referenced (if applicable):
None referenced
## L. Test Principle:
There are four different measuring principles employed in the sensors in the ABL90 FLEX analyzer.
Potentiometry: The potential of a sensor chain is recorded using a voltmeter, and related to the concentration of the sample (the Nernst equation). The potentiometric measuring principle is applied in the pH, pCO2, K+, Na+, Ca2+ and Cl- sensors.
Amperometry: The magnitude of an electrical current flowing through a sensor chain is proportional to the concentration of the substance being oxidized or reduced at an electrode in the chain. The Amperometric measuring principle is applied in the cGlu and cLac sensors.
Optical pO2: The optical system for pO2 is based on the ability of O2 to reduce the intensity and time constant of the phosphorescence from a phosphorescent dye that is in contact with the sample. This measuring principle is applied in the pO2 sensor.
{5}
Spectrophotometry: Light passes through a cuvette containing a hemolyzed blood sample. The specific wavelengths absorbed and their intensity generates an absorption spectrum used to calculate oximetry parameters. This measuring principle is used for measuring ctHb, sO2, FO2Hb, FCOHb, FHHb, FMetHb, and FHbF.
# M. Performance Characteristics (if/when applicable):
# 1. Analytical performance:
# a. Precision/Reproducibility:
An in-house, 20-day precision study was performed in accordance with the CLSI guideline EP5-A2. This study evaluated the precision performance of the ABL90 at three levels of whole blood glucose (approximately $18\mathrm{mg / dL}$ , $99\mathrm{mg / dL}$ , and $270\mathrm{mg / dL}$ ) in combinations at three different levels of pO2 concentrations (approximately $10\mathrm{mmHg}$ , $30\mathrm{mmHg}$ , and $>90\mathrm{mmHg}$ ). The heparinized, whole blood sample combinations were analyzed in duplicate, on three instruments, in 2 runs per day, for 20 days for a total of 240 runs per glucose-pO2 concentration combination. The between-day and total precision is summarized in the tables below.
Glucose Low
| | | | | Between-Day | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| ABL90 Analyzer | pO2 mmHg | n | Glucose Mean mg/dL | SD | CV% | SD | CV% |
| 1 | 10 | 80 | 17.5 | 0.54 | 3.1 | | |
| 2 | 10 | 80 | 18.5 | 1.26 | 6.8 | | |
| 3 | 10 | 80 | 17.8 | 0.52 | 2.9 | | |
| Combined | 10 | 240 | 17.9 | | | 0.8 | 4.7 |
| 1 | 30 | 80 | 17.6 | 0.50 | 2.8 | | |
| 2 | 30 | 80 | 18.5 | 1.14 | 6.1 | | |
| 3 | 30 | 80 | 17.8 | 0.46 | 2.6 | | |
| Combined | 30 | 240 | 18.0 | | | 0.8 | 4.3 |
| 1 | >90 | 80 | 17.7 | 0.49 | 2.8 | | |
| 2 | >90 | 80 | 18.6 | 1.10. | 5.9 | | |
| 3 | >90 | 80 | 17.9 | 0.42 | 2.3 | | |
| Combined | >90 | 240 | 18.1 | | | 0.7 | 4.1 |
Glucose Medium
| | | | | Between-Day | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| ABL90 Analyzer | pO2 mmHg | n | Glucose Mean mg/dL | SD | CV% | SD | CV% |
| 1 | 10 | 80 | 101.1 | 2.46 | 2.5 | | |
| 2 | 10 | 80 | 104.3 | 5.54 | 5.3 | | |
| 3 | 10 | 80 | 99.9 | 2.51 | 2.5 | | |
| Combined | 10 | 240 | 101.7 | | | 3.8 | 3.7 |
| 1 | 30 | 80 | 100.4 | 2.32 | 2.3 | | |
{6}
| 2 | 30 | 80 | 102.5 | 4.78 | 4.7 | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 3 | 30 | 80 | 100.2 | 2.28 | 2.3 | | |
| Combined | 30 | 240 | 101.0 | | | 3.3 | 3.3 |
| 1 | >90 | 80 | 100.3 | 2.29 | 2.3 | | |
| 2 | >90 | 80 | 101.5 | 4.72 | 4.7 | | |
| 3 | >90 | 80 | 101.8 | 2.16 | 2.1 | | |
| Combined | >90 | 240 | 101.2 | | | 3.3 | 3.2 |
Glucose High
| | | | | Between-Day | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| ABL90 Analyzer | pO2 mmHg | n | Glucose Mean mg/dL | SD | CV% | SD | CV% |
| 1 | 10 | 80 | 258.6 | 9.65 | 3.7 | | |
| 2 | 10 | 80 | 251.7 | 12.96 | 5.2 | | |
| 3 | 10 | 80 | 252.0 | 9.36 | 3.7 | | |
| Combined | 10 | 240 | 254.1 | | | 10.8 | 4.2 |
| 1 | 30 | 80 | 263.5 | 7.45 | 2.8 | | |
| 2 | 30 | 80 | 263.9 | 11.72 | 4.4 | | |
| 3 | 30 | 80 | 258.6 | 6.39 | 2.5 | | |
| Combined | 30 | 240 | 259.6 | | | 8.8 | 3.4 |
| 1 | >90 | 80 | 270.8 | 4.85 | 1.8 | | |
| 2 | >90 | 80 | 274.6 | 10.92 | 4.0 | | |
| 3 | >90 | 80 | 270.3 | 4.80 | 1.8 | | |
| Combined | >90 | 240 | 271.9 | | | 7.4 | 2.7 |
b. Linearity/assay reportable range:
The performance data submitted in the original submission, k092686 still apply.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The performance data submitted in the original submission, k092686 still apply.
d. Detection limit:
The performance data submitted in the original submission, k092686 still apply.
e. Analytical specificity:
An interference study was performed to evaluate the effect of pO2 and interfering substance in glucose measurement and to determine the upper measurable limit for glucose measurements in samples with pO2 concentrations between 10 and 80 mmHg. Freshly drawn heparinized human blood samples were tonometrated until the desired pO2 concentrations were achieved. Each glucose level was measured in series, starting with pO2 ≥90 mmHg as a control and alternating with the same concentration of glucose at lower pO2 concentrations of 80, 50, 25, 20, 15, and 10 mmHg. Seven glucose levels (9, 36, 79, 119, 180, 270, and 450 mg/dL) were measured in replicates of 6 on each of the 3 analyzers, with two runs on
{7}
different days throughout the test period. The total number of measurements during the study was 1512. The sponsor defines interference as $> \pm 10\%$ bias between the tested samples and the control samples. The data is summarized in the table below.
| Results of Interference Study: | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| % difference | pO2 | | | | | | |
| | | 10 | 15 | 20 | 25 | 50 | 80 |
| cGlu [mg/dL] | 9 | 3.3% | 3.1% | 3.4% | 1.1% | 3.8% | 0.0% |
| | 36 | 1.3% | 1.3% | 0.8% | 0.5% | 0.9% | 0.2% |
| | 79 | 2.0% | 1.6% | 0.7% | 0.8% | 0.9% | 0.6% |
| | 119 | 2.0% | 1.5% | 1.5% | 0.9% | 1.3% | 0.4% |
| | 180 | 4.7% | 2.7% | 2.5% | 0.9% | 0.3% | 0.6% |
| | 270 | 7.0% | 6.1% | 3.1% | 2.4% | 2.0% | 1.1% |
| | 450 | 13.6% | 9.3% | 7.1% | 3.8% | 5.0% | 0.7% |
Based on the interference results, the sponsor claims that the pO2 level between 10 to $25\mathrm{mmHg}$ will not significantly affect the glucose results of less than $270\mathrm{mg/dL}$ . In addition, the glucose result of $>270\mathrm{mg/dL}$ for sample with pO2 level between 10 and $25\mathrm{mmHg}$ will be suppressed and a message of "Glu not usable" will appear; the user should use an alternative method to measure the glucose result in this case. Sponsor has provided a warning of this limitation in the operator's manual.
f. Assay cut-off:
Not applicable.
# 2. Comparison studies:
# a. Method comparison with predicate device:
An in-house method comparison study was performed to verify bias of the glucose parameter between the ABL90 and the comparator device, the ABL735, when measuring whole blood samples with pO2 tension in the interval of $10\mathrm{mmHg}$ to $25\mathrm{mmHg}$ and glucose concentrations of between $9.0\mathrm{mg/dL}$ and $270\mathrm{mg/dL}$ . Three separate pairs of ABL90 and ABL735 analyzers were used throughout the method comparison study to simulate three external POC sites. Freshly drawn heparinized whole blood samples were tonometrated until desired pO2 levels were achieved. The samples were then measured on each of three ABL90/ABL735 paired analyzers. Testing was performed for 11 consecutive days. 510 data points were obtained on each of the ABL90/ABL735 pairs. ABL90 Flex vs. ABL735 regression analysis for glucose method comparison of samples with pO2 between $10\mathrm{mmHg}$ and $25\mathrm{mmHg}$ is summarized in the below table for each of the three instrument pairs:
ABL90 FLEX and ABL735 Method Comparison Regression Analysis
| Analyzer | n | Slope | Intercept | R2 |
| --- | --- | --- | --- | --- |
| 1 | 510 | 0.912 | 0.004 | 0.990 |
| 2 | 510 | 0.907 | 0.237 | 0.984 |
| 3 | 510 | 0.940 | 0.033 | 0.984 |
| Combined | 1530 | 0.921 | 0.084 | 0.990 |
{8}
b. Matrix comparison:
Only matrix recommended for ABL90FLEX is heparinized whole blood.
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable
b. Clinical specificity:
Not applicable
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
| Parameter | Population | Reference range | Cited from |
| --- | --- | --- | --- |
| pH, | Children, adults | 7.35-7.45 | Tietz 2008 |
| pCO2 | Female | 4.3-6.0 kPa | Tietz 2008 |
| | Male | 4.7-6.4 kPa | Tietz 2008 |
| pO2 | 2days- 60years | 11.0-14.4 kPa | Tietz 2008 |
| cK+ | Male, female | 3.4-4.5 meq/L | Tietz 1987 |
| cNa+ | Male, female | 136-146 meq/L | Tietz 1987 |
| cCa2+ | Adult | 2.30-2.66 meq/L | Tietz 2008 |
| cCl- | Adult | 98-107 meq/L | Tietz 2008 |
| cGlucose | Adult | 65-95 mg/dL | Tietz 2008 |
| cLactate | Female, male | 4.5-14.4 mg/L | Tietz 1987 |
| | At bed rest | 3.0-7.0 mg/L | Tietz 2008 |
| ctHb | Female | 12.0-16.0 g/dL | Tietz 1987 |
| | Male | 13.5-17.5 g/dL | Tietz 1987 |
N. Instrument Name:
ABL90 FLEX
O. System Descriptions:
1. Modes of Operation:
{9}
Single sample mode
2. Software:
FDA has reviewed applicant’s Hazard Analysis and software development processes for this line of product types:
Yes ☐ x ☐ or No ☐
3. Specimen Identification:
Single sample
4. Specimen Sampling and Handling:
This device is intended to be used with whole blood samples.
5. Calibration:
Two-point liquid calibration, calibration and QC reagents plus a waste reservoir are contained in one solution pack. "Smartchip" technology for unique identification and lot specific calibration and quality control data.
6. Quality Control:
QC reagents plus a waste reservoir are contained in one solution pack. "Smartchip" technology for unique identification and lot specific calibration and quality control data.
The sponsor states that the user should “Follow federal, state and local guidelines for testing quality control materials,” in the operator manual.
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The “Performance Characteristics” Section above:
None
Q. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
R. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.